Predictive Analytics For Dummies

1 - Title Page [Seite 3]
2 - Copyright Page [Seite 4]
3 - Table of Contents [Seite 5]
4 - Introduction [Seite 11]
5 - Part 1 Getting Started with Predictive Analytics [Seite 15]
5.1 - Chapter 1 Entering the Arena [Seite 17]
5.1.1 - Exploring Predictive Analytics [Seite 17]
5.1.1.1 - Mining data [Seite 18]
5.1.1.2 - Highlighting the model [Seite 19]
5.1.2 - Adding Business Value [Seite 20]
5.1.2.1 - Endless opportunities [Seite 21]
5.1.2.2 - Empowering your organization [Seite 22]
5.1.3 - Starting a Predictive Analytic Project [Seite 23]
5.1.3.1 - Business knowledge [Seite 24]
5.1.3.2 - Data-science team and technology [Seite 25]
5.1.3.3 - The Data [Seite 26]
5.1.4 - Ongoing Predictive Analytics [Seite 27]
5.1.5 - Forming Your Predictive Analytics Team [Seite 28]
5.1.5.1 - Hiring experienced practitioners [Seite 28]
5.1.5.2 - Demonstrating commitment and curiosity [Seite 29]
5.1.6 - Surveying the Marketplace [Seite 29]
5.1.6.1 - Responding to big data [Seite 30]
5.1.6.2 - Working with big data [Seite 30]
5.2 - Chapter 2 Predictive Analytics in the Wild [Seite 33]
5.2.1 - Online Marketing and Retail [Seite 35]
5.2.1.1 - Recommender systems [Seite 35]
5.2.1.2 - Personalized shopping on the Internet [Seite 36]
5.2.2 - Implementing a Recommender System [Seite 38]
5.2.2.1 - Collaborative filtering [Seite 38]
5.2.2.2 - Content-based filtering [Seite 46]
5.2.2.3 - Hybrid recommender systems [Seite 49]
5.2.3 - Target Marketing [Seite 51]
5.2.3.1 - Targeting using predictive modeling [Seite 52]
5.2.3.2 - Uplift modeling [Seite 53]
5.2.4 - Personalization [Seite 56]
5.2.4.1 - Online customer experience [Seite 56]
5.2.4.2 - Retargeting [Seite 57]
5.2.4.3 - Implementation [Seite 57]
5.2.4.4 - Optimizing using personalization [Seite 58]
5.2.4.5 - Similarities of Personalization and Recommendations [Seite 58]
5.2.5 - Content and Text Analytics [Seite 60]
5.3 - Chapter 3 Exploring Your Data Types and Associated Techniques [Seite 61]
5.3.1 - Recognizing Your Data Types [Seite 62]
5.3.1.1 - Structured and unstructured data [Seite 62]
5.3.1.2 - Static and streamed data [Seite 66]
5.3.2 - Identifying Data Categories [Seite 68]
5.3.2.1 - Attitudinal data [Seite 69]
5.3.2.2 - Behavioral data [Seite 70]
5.3.2.3 - Demographic data [Seite 71]
5.3.3 - Generating Predictive Analytics [Seite 71]
5.3.3.1 - Data-driven analytics [Seite 72]
5.3.3.2 - User-driven analytics [Seite 74]
5.3.4 - Connecting to Related Disciplines [Seite 75]
5.3.4.1 - Statistics [Seite 75]
5.3.4.2 - Data mining [Seite 76]
5.3.4.3 - Machine learning [Seite 77]
5.4 - Chapter 4 Complexities of Data [Seite 79]
5.4.1 - Finding Value in Your Data [Seite 80]
5.4.1.1 - Delving into your data [Seite 80]
5.4.1.2 - Data validity [Seite 80]
5.4.1.3 - Data variety [Seite 81]
5.4.2 - Constantly Changing Data [Seite 82]
5.4.2.1 - Data velocity [Seite 82]
5.4.2.2 - High volume of data [Seite 83]
5.4.3 - Complexities in Searching Your Data [Seite 83]
5.4.3.1 - Keyword-based search [Seite 84]
5.4.3.2 - Semantic-based search [Seite 84]
5.4.3.3 - Contextual search [Seite 86]
5.4.4 - Differentiating Business Intelligence from Big-Data Analytics [Seite 89]
5.4.5 - Exploration of Raw Data [Seite 90]
5.4.5.1 - Identifying data attributes [Seite 90]
5.4.5.2 - Exploring common data visualizations [Seite 91]
5.4.5.3 - Tabular visualizations [Seite 91]
5.4.5.4 - Word clouds [Seite 92]
5.4.5.5 - Flocking birds as a novel data representation [Seite 93]
5.4.5.6 - Graph charts [Seite 95]
5.4.5.7 - Common visualizations [Seite 97]
6 - Part 2 Incorporating Algorithms in Your Models [Seite 99]
6.1 - Chapter 5 Applying Models [Seite 101]
6.1.1 - Modeling Data [Seite 102]
6.1.1.1 - Models and simulation [Seite 102]
6.1.1.2 - Categorizing models [Seite 104]
6.1.1.3 - Describing and summarizing data [Seite 106]
6.1.1.4 - Making better business decisions [Seite 107]
6.1.2 - Healthcare Analytics Case Studies [Seite 107]
6.1.2.1 - Google Flu Trends [Seite 107]
6.1.2.2 - Cancer survivability predictors [Seite 109]
6.1.3 - Social and Marketing Analytics Case Studies [Seite 111]
6.1.3.1 - Target store predicts pregnant women [Seite 111]
6.1.3.2 - Twitter-based predictors of earthquakes [Seite 112]
6.1.3.3 - Twitter-based predictors of political campaign outcomes [Seite 113]
6.1.3.4 - Tweets as predictors for the stock market [Seite 115]
6.1.3.5 - Predicting variation of stock prices from news articles [Seite 116]
6.1.3.6 - Analyzing New York City's bicycle usage [Seite 117]
6.1.3.7 - Predictions and responses [Seite 120]
6.1.3.8 - Data compression [Seite 121]
6.1.4 - Prognostics and its Relation to Predictive Analytics [Seite 122]
6.1.5 - The Rise of Open Data [Seite 123]
6.2 - Chapter 6 Identifying Similarities in Data [Seite 125]
6.2.1 - Explaining Data Clustering [Seite 126]
6.2.2 - Converting Raw Data into a Matrix [Seite 130]
6.2.2.1 - Creating a matrix of terms in documents [Seite 130]
6.2.2.2 - Term selection [Seite 131]
6.2.3 - Identifying Groups in Your Data [Seite 132]
6.2.3.1 - K-means clustering algorithm [Seite 132]
6.2.3.2 - Clustering by nearest neighbors [Seite 136]
6.2.3.3 - Density-based algorithms [Seite 140]
6.2.4 - Finding Associations in Data Items [Seite 142]
6.2.5 - Applying Biologically Inspired Clustering Techniques [Seite 146]
6.2.5.1 - Birds flocking: Flock by Leader algorithm [Seite 146]
6.2.5.2 - Ant colonies [Seite 153]
6.3 - Chapter 7 Predicting the Future Using Data Classification [Seite 157]
6.3.1 - Explaining Data Classification [Seite 159]
6.3.2 - Introducing Data Classification to Your Business [Seite 162]
6.3.3 - Exploring the Data-Classification Process [Seite 164]
6.3.4 - Using Data Classification to Predict the Future [Seite 166]
6.3.4.1 - Decision trees [Seite 166]
6.3.4.2 - Algorithms for Generating Decision Trees [Seite 169]
6.3.4.3 - Support vector machine [Seite 173]
6.3.5 - Ensemble Methods to Boost Prediction Accuracy [Seite 175]
6.3.5.1 - Naïve Bayes classification algorithm [Seite 176]
6.3.5.2 - The Markov Model [Seite 182]
6.3.5.3 - Linear regression [Seite 187]
6.3.5.4 - Neural networks [Seite 187]
6.3.6 - Deep Learning [Seite 189]
7 - Part 3 Developing a Roadmap [Seite 195]
7.1 - Chapter 8 Convincing Your Management to Adopt Predictive Analytics [Seite 197]
7.1.1 - Making the Business Case [Seite 198]
7.1.2 - Gathering Support from Stakeholders [Seite 205]
7.1.3 - Presenting Your Proposal [Seite 216]
7.2 - Chapter 9 Preparing Data [Seite 219]
7.2.1 - Listing the Business Objectives [Seite 220]
7.2.2 - Processing Your Data [Seite 222]
7.2.2.1 - Identifying the data [Seite 222]
7.2.2.2 - Cleaning the data [Seite 223]
7.2.2.3 - Generating any derived data [Seite 225]
7.2.2.4 - Reducing the dimensionality of your data [Seite 225]
7.2.2.5 - Applying principal component analysis [Seite 226]
7.2.2.6 - Leveraging singular value decomposition [Seite 228]
7.2.3 - Working with Features [Seite 229]
7.2.4 - Structuring Your Data [Seite 234]
7.2.4.1 - Extracting, transforming and loading your data [Seite 235]
7.2.4.2 - Keeping the data up to date [Seite 236]
7.2.4.3 - Outlining testing and test data [Seite 236]
7.3 - Chapter 10 Building a Predictive Model [Seite 239]
7.3.1 - Getting Started [Seite 240]
7.3.1.1 - Defining your business objectives [Seite 242]
7.3.1.2 - Preparing your data [Seite 243]
7.3.1.3 - Choosing an algorithm [Seite 246]
7.3.2 - Developing and Testing the Model [Seite 247]
7.3.3 - Going Live with the Model [Seite 252]
7.4 - Chapter 11 Visualization of Analytical Results [Seite 255]
7.4.1 - Visualization as a Predictive Tool [Seite 256]
7.4.2 - Evaluating Your Visualization [Seite 259]
7.4.3 - Visualizing Your Model's Analytical Results [Seite 261]
7.4.3.1 - Visualizing hidden groupings in your data [Seite 261]
7.4.3.2 - Visualizing data classification results [Seite 262]
7.4.3.3 - Visualizing outliers in your data [Seite 264]
7.4.3.4 - Visualization of Decision Trees [Seite 264]
7.4.3.5 - Visualizing predictions [Seite 266]
7.4.4 - Novel Visualization in Predictive Analytics [Seite 268]
7.4.5 - Big Data Visualization Tools [Seite 272]
7.4.5.1 - Tableau [Seite 273]
7.4.5.2 - Google Charts [Seite 273]
7.4.5.3 - Plotly [Seite 273]
7.4.5.4 - Infogram [Seite 274]
8 - Part 4 Programming Predictive Analytics [Seite 275]
8.1 - Chapter 12 Creating Basic Prediction Examples [Seite 277]
8.1.1 - Installing the Software Packages [Seite 278]
8.1.1.1 - Installing Python [Seite 278]
8.1.1.2 - Installing the machine-learning module [Seite 280]
8.1.1.3 - Installing the dependencies [Seite 284]
8.1.2 - Preparing the Data [Seite 288]
8.1.3 - Making Predictions Using Classification Algorithms [Seite 290]
8.1.3.1 - Creating a supervised learning model with SVM [Seite 291]
8.1.3.2 - Creating a supervised learning model with logistic regression [Seite 298]
8.1.3.3 - Creating a supervised learning model with random forest [Seite 305]
8.1.3.4 - Comparing the classification models [Seite 307]
8.2 - Chapter 13 Creating Basic Examples of Unsupervised Predictions [Seite 309]
8.2.1 - Getting the Sample Dataset [Seite 310]
8.2.2 - Using Clustering Algorithms to Make Predictions [Seite 311]
8.2.2.1 - Comparing clustering models [Seite 311]
8.2.2.2 - Creating an unsupervised learning model with K-means [Seite 312]
8.2.2.3 - Creating an unsupervised learning model with DBSCAN [Seite 324]
8.2.2.4 - Creating an unsupervised learning model with mean shift [Seite 328]
8.3 - Chapter 14 Predictive Modeling with R [Seite 333]
8.3.1 - Programming in R [Seite 335]
8.3.1.1 - Installing R [Seite 335]
8.3.1.2 - Installing RStudio [Seite 336]
8.3.1.3 - Getting familiar with the environment [Seite 337]
8.3.1.4 - Learning just a bit of R [Seite 338]
8.3.2 - Making Predictions Using R [Seite 344]
8.3.2.1 - Predicting using regression [Seite 344]
8.3.2.2 - Using classification to predict [Seite 355]
8.3.2.3 - Classification by random forest [Seite 364]
8.4 - Chapter 15 Avoiding Analysis Traps [Seite 369]
8.4.1 - Data Challenges [Seite 370]
8.4.1.1 - Outlining the limitations of the data [Seite 371]
8.4.1.2 - Dealing with extreme cases (outliers) [Seite 374]
8.4.1.3 - Data smoothing [Seite 377]
8.4.1.4 - Curve fitting [Seite 381]
8.4.1.5 - Keeping the assumptions to a minimum [Seite 384]
8.4.2 - Analysis Challenges [Seite 385]
9 - Part 5 Executing Big Data [Seite 391]
9.1 - Chapter 16 Targeting Big Data [Seite 393]
9.1.1 - Major Technological Trends in Predictive Analytics [Seite 394]
9.1.1.1 - Exploring predictive analytics as a service [Seite 394]
9.1.1.2 - Aggregating distributed data for analysis [Seite 395]
9.1.1.3 - Real-time data-driven analytics [Seite 397]
9.1.2 - Applying Open-Source Tools to Big Data [Seite 398]
9.1.2.1 - Apache Hadoop [Seite 398]
9.1.2.2 - Apache Spark [Seite 404]
9.2 - Chapter 17 Getting Ready for Enterprise Analytics [Seite 409]
9.2.1 - Analytics as a Service [Seite 413]
9.2.1.1 - Google Analytics [Seite 413]
9.2.1.2 - IBM Watson [Seite 415]
9.2.1.3 - Microsoft Revolution R Enterprise [Seite 415]
9.2.2 - Preparing for a Proof-of-Value of Predictive Analytics Prototype [Seite 416]
9.2.2.1 - Prototyping for predictive analytics [Seite 416]
9.2.2.2 - Testing your predictive analytics model [Seite 419]
10 - Part 6 The Part of Tens [Seite 421]
10.1 - Chapter 18 Ten Reasons to Implement Predictive Analytics [Seite 423]
10.2 - Chapter 19 Ten Steps to Build a Predictive Analytic Model [Seite 433]
11 - Index [Seite 443]
12 - EULA [Seite 459]